---
id: "titanic"
slug: "titanic"
name: "Titanic"
domain: "Maritime Safety & Actuarial Risk Analysis"
taskType: "binary_classification"
numRows: 1309
numColumns: 12
targetColumn: "survived"
primaryMetric: "1 - AUC Error"
primaryScore: "0.1229"
parquetUrl: "https://huggingface.co/datasets/carlahq/demo-tabular-benchmarks/resolve/main/data/titanic/titanic.parquet"
spreadsheetUrl: "https://docs.google.com/spreadsheets/d/1bt2x-OV7e2Xq1RmMtn964gSv9oqjoJxGLEs9jv7jdnU/edit?usp=sharing"
canonicalUrl: "https://carlahq.eu/datasets/titanic"
---

# Dataset: Titanic (titanic)

> Canonical 1,309-record benchmark dataset describing Titanic passenger demographics, socio-economic markers, and cabin locations to predict binary survival outcomes.

## Dataset Overview

| Attribute | Value |
| :--- | :--- |
| **Task Type** | `binary_classification` |
| **Business Domain** | Maritime Safety & Actuarial Risk Analysis |
| **Target Column** | `survived` |
| **Rows (Instances)** | 1,309 |
| **Features (Columns)** | 12 |
| **Primary Evaluation Metric** | 1 - AUC Error |
| **Best Benchmark Score** | **0.1229** |

## Business Decision Context
**Context:** Passenger evacuation protocols and maritime safety logistics during mass-casualty emergency operations, historically governed by triage heuristics such as 'women and children first' and stratified socio-economic access to survival resources.
**Objective:** Predict the binary survival probability of individual passengers based on socio-economic tier, demographic profile, cabin positioning, and family accompaniment.
**Decision Impact:** Enables historical casualty auditing, safety triage simulation, and actuarial disaster loss modeling where false positives (misclassifying deceased passengers as survivors) distort survival resource allocations and emergency egress planning.

## Feature Schema
| Column Name | Data Type | Role | Distinct Values | Missing Values (%) | Description |
| :--- | :--- | :--- | :--- | :--- | :--- |
| `survived` | `numeric` | target | 2 | 0 | Binary passenger outcome indicating whether the individual survived the disaster (0 = Did not survive / Deceased, 1 = Survived). |
| `pclass` | `numeric` | feature | 3 | 0 | Ticket class representing socio-economic status (1 = 1st Class / Upper Tier, 2 = 2nd Class / Middle Tier, 3 = 3rd Class / Lower Tier). |
| `name` | `string` | feature | 1,307 | 0 | Full formal name and honorific title (e.g. Mr., Mrs., Miss, Master, Dr., Rev.) of the passenger. |
| `sex` | `categorical` | feature | 2 | 0 | Biological sex / gender of the passenger (female, male). |
| `age` | `numeric` | feature | 98 | 263 | Age of the passenger in years (fractional for infants under 1 year old; missing values represent unknown ages). |
| `sibsp` | `numeric` | feature | 7 | 0 | Total count of siblings (brother, sister, stepbrother, stepsister) or spouses (husband, wife) traveling with the passenger. |
| `parch` | `numeric` | feature | 8 | 0 | Total count of parents (mother, father) or children (daughter, son, stepdaughter, stepson) traveling with the passenger. |
| `ticket` | `string` | feature | 929 | 0 | Alphanumeric ticket booking identifier or serial reference assigned to the passenger. |
| `fare` | `numeric` | feature | 281 | 1 | Total passenger fare paid in pre-1970 British Pounds (£) for boarding the voyage. |
| `cabin` | `string` | feature | 186 | 1014 | Assigned deck and stateroom cabin identifier (e.g. B5, C22 C26). Deck letter reflects vertical proximity to boat deck. |
| `embarked` | `categorical` | feature | 3 | 2 | Port where the passenger boarded the vessel (C = Cherbourg, Q = Queenstown, S = Southampton). |
| `boat` | `categorical` | leakage | 27 | 823 | Identification number or letter of the rescue lifeboat used by surviving passengers (post-event indicator). |
| `body` | `numeric` | leakage | 121 | 1188 | Coroner recovery identification index assigned to deceased passenger bodies retrieved from the ocean. |
| `homedest` | `string` | feature | 369 | 564 | Geographic origin / home city and ultimate travel destination intended by the passenger. |

## Empirical Benchmark Leaderboard
| Rank | Algorithm / Model | Model Family | Runtime | Accuracy | ROC AUC | F1-Score |
| :--- | :--- | :--- | :--- | :--- | :--- | :--- |
| 1 | **EXAONE Tabular** | Tabular Foundation Model | PyTorch/Python | **82.96%** | 0.8854 | 0.7569 |
| 2 | **Google TabFM v1.0** | Tabular Foundation Model | PyTorch/Python | **82.47%** | 0.8834 | 0.7509 |
| 3 | **Streaming nanotabicl** | Tabular Foundation Model | PyTorch/Python | **82.38%** | 0.8771 | 0.7498 |
| 4 | **Full TabICLv2 (PyTorch Reference)** | Tabular Foundation Model | PyTorch/Python | **82.38%** | 0.8771 | 0.7498 |
| 5 | **nanotabicl Vanilla** | Tabular Foundation Model | PyTorch/Python | **82.35%** | 0.8771 | 0.7494 |
| 6 | **Carla Engine (TabICLv2 WebGPU)** | Tabular Foundation Model | Browser | **82.24%** | 0.8749 | 0.7477 |
| 7 | **TabPFN v3** | Tabular Foundation Model | PyTorch/Python | **81.13%** | 0.8640 | 0.7327 |

### Repeated Cross-Validation Fold Scores (TabICLv2 Reference)
| Fold | Train Samples | Test Samples | Metric Score | Latency |
| :--- | :--- | :--- | :--- | :--- |
| Fold 0 | 872 | 437 | 0.1413 | 777ms |
| Fold 1 | 873 | 436 | 0.1292 | 825ms |
| Fold 2 | 873 | 436 | 0.1289 | 767ms |
| Fold 0 | 872 | 437 | 0.1218 | 795ms |
| Fold 1 | 873 | 436 | 0.1496 | 781ms |
| Fold 2 | 873 | 436 | 0.1036 | 771ms |
| Fold 0 | 872 | 437 | 0.0988 | 768ms |
| Fold 1 | 873 | 436 | 0.1318 | 763ms |
| Fold 2 | 873 | 436 | 0.1244 | 784ms |
| Fold 0 | 872 | 437 | 0.1408 | 767ms |
| Fold 1 | 873 | 436 | 0.1243 | 777ms |
| Fold 2 | 873 | 436 | 0.1135 | 766ms |
| Fold 0 | 872 | 437 | 0.1403 | 786ms |
| Fold 1 | 873 | 436 | 0.0987 | 766ms |
| Fold 2 | 873 | 436 | 0.1104 | 771ms |
| Fold 0 | 872 | 437 | 0.1356 | 767ms |
| Fold 1 | 873 | 436 | 0.1015 | 780ms |
| Fold 2 | 873 | 436 | 0.1383 | 791ms |
| Fold 0 | 872 | 437 | 0.1139 | 764ms |
| Fold 1 | 873 | 436 | 0.1234 | 758ms |
| Fold 2 | 873 | 436 | 0.1208 | 775ms |
| Fold 0 | 872 | 437 | 0.1686 | 772ms |
| Fold 1 | 873 | 436 | 0.1181 | 766ms |
| Fold 2 | 873 | 436 | 0.0964 | 771ms |
| Fold 0 | 872 | 437 | 0.1260 | 783ms |
| Fold 1 | 873 | 436 | 0.1499 | 771ms |
| Fold 2 | 873 | 436 | 0.0855 | 779ms |
| Fold 0 | 872 | 437 | 0.1175 | 779ms |
| Fold 1 | 873 | 436 | 0.1009 | 785ms |
| Fold 2 | 873 | 436 | 0.1340 | 764ms |

## Provenance & Downloadable Artifacts
- **Dataset Parquet File:** [Direct Parquet Download](https://huggingface.co/datasets/carlahq/demo-tabular-benchmarks/resolve/main/data/titanic/titanic.parquet)
- **Google Sheets Interactive Demo:** [Open in Google Sheets](https://docs.google.com/spreadsheets/d/1bt2x-OV7e2Xq1RmMtn964gSv9oqjoJxGLEs9jv7jdnU/edit?usp=sharing)
- **OpenML Source:** [OpenML Dataset](https://www.openml.org/d/40945)
- **Academic Paper / Citation:** [Read Research Paper](https://hbiostat.org/data/repo/titanic.html)
- **Canonical HTML Page:** [https://carlahq.eu/datasets/titanic](https://carlahq.eu/datasets/titanic)